Empowering Vector Architectures for ML: The CAMP Architecture for Matrix Multiplication
Authors:
- Mohammadreza Esmali NojehdehMNMohammadreza Esmali Nojehdeh
- Hossein MokhtarniaHMHossein Mokhtarnia
- Julian PavonJPJulian Pavon
- Narcís RodasNRNarcís Rodas
- Roger Figueras BaguéRBRoger Figueras Bagué
- Enrico ReggianiEREnrico Reggiani
- Miquel MoretoMMMiquel Moreto
- Osman UnsalOUOsman Unsal
- Adrián CristalACAdrián Cristal
- Eduard AyguadéEAEduard Ayguadé
Open Access
- 17 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1300-1315
Abstract
No abstract availableAll Related Versions
Funding Information
- European High-Performance Computing Joint Undertaking (JU) (Grant Agreement No. 101202459 (DARE SGA1 Project))
- MICIU/AEI (Agencia Estatal de Investigaci쎳n, Spain) (Project No. PCI2024-161687-3 Project No. PID2023-146511NB-I00 Project No. PID2023-147979NB-C21)
- European Union NextGenerationEU /PRTR (Linked to PCI2024-161687-3)
- Spanish Ministry for Digital Transformation and Public Service (REGAGE22e00058408992 (Recovery Transformation and Resilience Plan NextGenerationEU))
- Generalitat de Catalunya (Contract No. 2021-SGR-00763)
- LenovoBSC Framework Contract (2020) ()
This publication has 37 references indexed in Scilit:
- Publisher Correction: Scientific discovery in the age of artificial intelligenceNature, 2023
- Task-aware Scheduling and Performance Optimization on Yitian710 SoC for GEMM-based Workloads on the Cloud2023
- Mix-GEMM: An efficient HW-SW Architecture for Mixed-Precision Quantized Deep Neural Networks Inference on Edge Devices2023
- Built for the Edge: The Next-Generation Intel® Xeon D 2700 & 1700 processors2022
- Sargantana: A 1 GHz+ In-Order RISC-V Processor with SIMD Vector Extensions in 22nm FD-SOI2022
- Power/Performance/Area Evaluations for Next-Generation HPC Processors using the A64FX Chip2021
- SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning2021
- Preliminary Performance Evaluation of the Fujitsu A64FX Using HPC Applications2020
- A^3: Accelerating Attention Mechanisms in Neural Networks with Approximation2020
- PULP-NN: accelerating quantized neural networks on parallel ultra-low-power RISC-V processorsPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2019